Tradeoffs in Real-Time Robotic Task Design with Neuroevolution Learning for Imprecise Computation

We present a study on the tradeoffs between three design parameters for robotic task systems that function in partially unknown and unstructured environments, and under timing constraints. The design space of these robotic tasks must incorporate at least three dimensions: (1) the amount of training effort to teach the robot to perform the task, (2) the time available to complete the task from the point when the command is given to perform the task, and (3) the quality of the result from performing the task. This paper presents a tradeoff study in this design space for a common robotic task, specifically, grasping of unknown objects in unstructured environments. The imprecise computation model is used to provide a framework for this study. The results were validated with a real robot and contribute to the development of a systematic approach for designing robotic task systems that must function in environments like flexible manufacturing systems of the future.

[1]  Jan Peters,et al.  Reinforcement learning in robotics: A survey , 2013, Int. J. Robotics Res..

[2]  Ashutosh Saxena,et al.  Robotic Grasping of Novel Objects , 2006, NIPS.

[3]  Quoc V. Le,et al.  Grasping novel objects with depth segmentation , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Tomás Lozano-Pérez,et al.  Imitation Learning of Whole-Body Grasps , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Hod Lipson,et al.  Evolutionary Robotics for Legged Machines: From Simulation to Physical Reality , 2006, IAS.

[6]  Joel Lehman,et al.  Grasping novel objects with a dexterous robotic hand through neuroevolution , 2014, CICA.

[7]  Glauco Augusto de Paula Caurin,et al.  Learning how to grasp based on neural network retraining , 2013, Adv. Robotics.

[8]  Roland Philippsen,et al.  Implementation and stability analysis of prioritized whole-body compliant controllers on a wheeled humanoid robot in uneven terrains , 2013, Autonomous Robots.

[9]  Riccardo Bettati,et al.  Imprecise computations , 1994, Proc. IEEE.

[10]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[11]  Henrik I. Christensen,et al.  Automatic grasp planning using shape primitives , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[12]  Ashutosh Saxena,et al.  Monocular depth perception and robotic grasping of novel objects , 2009 .

[13]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[14]  Risto Miikkulainen,et al.  Architecture of a cyberphysical avatar , 2013, 2013 ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS).

[15]  Oussama Khatib,et al.  Compliant Control of Multicontact and Center-of-Mass Behaviors in Humanoid Robots , 2010, IEEE Transactions on Robotics.

[16]  Peter K. Allen,et al.  An SVM learning approach to robotic grasping , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[17]  Lawson L. S. Wong,et al.  Learning Grasp Strategies with Partial Shape Information , 2008, AAAI.

[18]  Peter K. Allen,et al.  Graspit! A versatile simulator for robotic grasping , 2004, IEEE Robotics & Automation Magazine.

[19]  Nick Jakobi,et al.  Minimal simulations for evolutionary robotics , 1998 .

[20]  Quoc V. Le,et al.  Learning to grasp objects with multiple contact points , 2010, 2010 IEEE International Conference on Robotics and Automation.

[21]  Ashutosh Saxena,et al.  Robotic Grasping of Novel Objects using Vision , 2008, Int. J. Robotics Res..

[22]  Juan López Coronado,et al.  A modular neural network architecture for step-wise learning of grasping tasks , 2007, Neural Networks.

[23]  Nasser Rezzoug,et al.  Robotic Grasping: A Generic Neural Network Architecture , 2006 .

[24]  Leslie Pack Kaelbling,et al.  Grasping POMDPs , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.